Deep Self-Taught Learning for Handwritten Character Recognition

Details Deep Self-Taught Learning for Handwritten Character Recognition Deep Self-Taught Learning for Handwritten Character Recognition

2010-09-18

arxiv.org/abs/1009.3589v1

Computer Science

Learning

Scientific paper

Recent theoretical and empirical work in statistical machine learning has demonstrated the importance of learning algorithms for deep architectures, i.e., function classes obtained by composing multiple non-linear transformations. Self-taught learning (exploiting unlabeled examples or examples from other distributions) has already been applied to deep learners, but mostly to show the advantage of unlabeled examples. Here we explore the advantage brought by {\em out-of-distribution examples}. For this purpose we developed a powerful generator of stochastic variations and noise processes for character images, including not only affine transformations but also slant, local elastic deformations, changes in thickness, background images, grey level changes, contrast, occlusion, and various types of noise. The out-of-distribution examples are obtained from these highly distorted images or by including examples of object classes different from those in the target test set. We show that {\em deep learners benefit more from out-of-distribution examples than a corresponding shallow learner}, at least in the area of handwritten character recognition. In fact, we show that they beat previously published results and reach human-level performance on both handwritten digit classification and 62-class handwritten character recognition.

Affiliated with

Also associated with

No associations

Rating

Deep Self-Taught Learning for Handwritten Character Recognition does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Deep Self-Taught Learning for Handwritten Character Recognition, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Deep Self-Taught Learning for Handwritten Character Recognition will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-408495